zola/components/library/src/sorting.rs

193 lines
6.4 KiB
Rust
Raw Normal View History

2018-10-02 14:42:34 +00:00
use std::cmp::Ordering;
2018-10-31 07:18:57 +00:00
use chrono::NaiveDateTime;
2018-10-02 14:42:34 +00:00
use rayon::prelude::*;
2019-09-16 09:44:39 +00:00
use slotmap::DefaultKey;
2018-10-02 14:42:34 +00:00
use content::Page;
2018-10-05 17:34:27 +00:00
/// Used by the RSS feed
/// There to not have to import sorting stuff in the site crate
Fix clippy warnings (#744) Clippy is returning some warnings. Let's fix or explicitly ignore them. In particular: - In `components/imageproc/src/lib.rs`, we implement `Hash` explicitly but derive `PartialEq`. We need to maintain the property that two keys being equal implies the hashes of those two keys are equal. Our `Hash` implementations preserve this, so we'll explicitly ignore the warnings. - In `components/site/src/lib.rs`, we were calling `.into()` on some values that are already of the correct type. - In `components/site/src/lib.rs`, we were using `.map(|x| *x)` in iterator chains to remove a level of indirection; we can instead say `.copied()` (introduced in Rust v1.36) or `.cloned()`. Using `.copied` here is better from a type-checking point of view, but we'll use `.cloned` for now as Rust v1.36 was only recently released. - In `components/templates/src/filters.rs` and `components/utils/src/site.rs`, we were taking `HashMap`s as function arguments but not generically accepting alternate `Hasher` implementations. - In `src/cmd/check.rs`, we use `env::current_dir()` as a default value, but our use of `unwrap_or` meant that we would always retrieve the current directory even when not needed. - In `components/errors/src/lib.rs`, we can use `if let` rather than `match`. - In `components/library/src/content/page.rs`, we can collapse a nested conditional into `else if let ...`. - In `components/library/src/sorting.rs`, a function takes `&&Page` arguments. Clippy warns about this for efficiency reasons, but we're doing it here to match a particular sorting API, so we'll explicitly ignore the warning.
2019-07-12 08:29:44 +00:00
#[allow(clippy::trivially_copy_pass_by_ref)]
2018-10-02 14:42:34 +00:00
pub fn sort_actual_pages_by_date(a: &&Page, b: &&Page) -> Ordering {
let ord = b.meta.datetime.unwrap().cmp(&a.meta.datetime.unwrap());
if ord == Ordering::Equal {
a.permalink.cmp(&b.permalink)
} else {
ord
}
}
2018-10-05 17:34:27 +00:00
/// Takes a list of (page key, date, permalink) and sort them by dates if possible
/// Pages without date will be put in the unsortable bucket
/// The permalink is used to break ties
2019-09-16 09:44:39 +00:00
pub fn sort_pages_by_date(pages: Vec<(&DefaultKey, Option<NaiveDateTime>, &str)>) -> (Vec<DefaultKey>, Vec<DefaultKey>) {
2018-10-31 07:18:57 +00:00
let (mut can_be_sorted, cannot_be_sorted): (Vec<_>, Vec<_>) =
pages.into_par_iter().partition(|page| page.1.is_some());
can_be_sorted.par_sort_unstable_by(|a, b| {
let ord = b.1.unwrap().cmp(&a.1.unwrap());
if ord == Ordering::Equal {
a.2.cmp(&b.2)
} else {
ord
}
});
2018-10-02 14:42:34 +00:00
(can_be_sorted.iter().map(|p| *p.0).collect(), cannot_be_sorted.iter().map(|p| *p.0).collect())
}
2018-10-05 17:34:27 +00:00
/// Takes a list of (page key, weight, permalink) and sort them by weight if possible
/// Pages without weight will be put in the unsortable bucket
/// The permalink is used to break ties
2019-09-16 09:44:39 +00:00
pub fn sort_pages_by_weight(pages: Vec<(&DefaultKey, Option<usize>, &str)>) -> (Vec<DefaultKey>, Vec<DefaultKey>) {
2018-10-31 07:18:57 +00:00
let (mut can_be_sorted, cannot_be_sorted): (Vec<_>, Vec<_>) =
pages.into_par_iter().partition(|page| page.1.is_some());
can_be_sorted.par_sort_unstable_by(|a, b| {
let ord = a.1.unwrap().cmp(&b.1.unwrap());
if ord == Ordering::Equal {
a.2.cmp(&b.2)
} else {
ord
}
});
2018-10-02 14:42:34 +00:00
(can_be_sorted.iter().map(|p| *p.0).collect(), cannot_be_sorted.iter().map(|p| *p.0).collect())
}
2018-10-05 17:34:27 +00:00
/// Find the lighter/heavier and earlier/later pages for all pages having a date/weight
2019-09-16 09:44:39 +00:00
pub fn find_siblings(sorted: &[DefaultKey]) -> Vec<(DefaultKey, Option<DefaultKey>, Option<DefaultKey>)> {
2018-10-02 14:42:34 +00:00
let mut res = Vec::with_capacity(sorted.len());
let length = sorted.len();
2019-07-19 09:10:28 +00:00
for (i, key) in sorted.iter().enumerate() {
let mut with_siblings = (*key, None, None);
2018-10-02 14:42:34 +00:00
if i > 0 {
2019-07-19 09:10:28 +00:00
// lighter / later
with_siblings.1 = Some(sorted[i - 1]);
2018-10-02 14:42:34 +00:00
}
if i < length - 1 {
2019-07-19 09:10:28 +00:00
// heavier/earlier
with_siblings.2 = Some(sorted[i + 1]);
2018-10-02 14:42:34 +00:00
}
res.push(with_siblings);
}
res
}
#[cfg(test)]
mod tests {
use slotmap::DenseSlotMap;
use std::path::PathBuf;
2018-10-02 14:42:34 +00:00
2018-10-31 07:18:57 +00:00
use super::{find_siblings, sort_pages_by_date, sort_pages_by_weight};
2018-10-02 14:42:34 +00:00
use content::Page;
2018-10-31 07:18:57 +00:00
use front_matter::PageFrontMatter;
2018-10-02 14:42:34 +00:00
fn create_page_with_date(date: &str) -> Page {
let mut front_matter = PageFrontMatter::default();
front_matter.date = Some(date.to_string());
front_matter.date_to_datetime();
Page::new("content/hello.md", front_matter, &PathBuf::new())
2018-10-02 14:42:34 +00:00
}
fn create_page_with_weight(weight: usize) -> Page {
let mut front_matter = PageFrontMatter::default();
front_matter.weight = Some(weight);
Page::new("content/hello.md", front_matter, &PathBuf::new())
2018-10-02 14:42:34 +00:00
}
#[test]
fn can_sort_by_dates() {
let mut dense = DenseSlotMap::new();
let page1 = create_page_with_date("2018-01-01");
let key1 = dense.insert(page1.clone());
let page2 = create_page_with_date("2017-01-01");
let key2 = dense.insert(page2.clone());
let page3 = create_page_with_date("2019-01-01");
let key3 = dense.insert(page3.clone());
let input = vec![
(&key1, page1.meta.datetime, page1.permalink.as_ref()),
(&key2, page2.meta.datetime, page2.permalink.as_ref()),
(&key3, page3.meta.datetime, page3.permalink.as_ref()),
];
let (pages, _) = sort_pages_by_date(input);
// Should be sorted by date
assert_eq!(pages[0], key3);
assert_eq!(pages[1], key1);
assert_eq!(pages[2], key2);
}
#[test]
fn can_sort_by_weight() {
let mut dense = DenseSlotMap::new();
let page1 = create_page_with_weight(2);
let key1 = dense.insert(page1.clone());
let page2 = create_page_with_weight(3);
let key2 = dense.insert(page2.clone());
let page3 = create_page_with_weight(1);
let key3 = dense.insert(page3.clone());
let input = vec![
(&key1, page1.meta.weight, page1.permalink.as_ref()),
(&key2, page2.meta.weight, page2.permalink.as_ref()),
(&key3, page3.meta.weight, page3.permalink.as_ref()),
];
let (pages, _) = sort_pages_by_weight(input);
// Should be sorted by weight
assert_eq!(pages[0], key3);
assert_eq!(pages[1], key1);
assert_eq!(pages[2], key2);
}
#[test]
fn ignore_page_with_missing_field() {
let mut dense = DenseSlotMap::new();
let page1 = create_page_with_weight(2);
let key1 = dense.insert(page1.clone());
let page2 = create_page_with_weight(3);
let key2 = dense.insert(page2.clone());
let page3 = create_page_with_date("2019-01-01");
let key3 = dense.insert(page3.clone());
let input = vec![
(&key1, page1.meta.weight, page1.permalink.as_ref()),
(&key2, page2.meta.weight, page2.permalink.as_ref()),
(&key3, page3.meta.weight, page3.permalink.as_ref()),
];
2018-10-31 07:18:57 +00:00
let (pages, unsorted) = sort_pages_by_weight(input);
2018-10-02 14:42:34 +00:00
assert_eq!(pages.len(), 2);
assert_eq!(unsorted.len(), 1);
}
#[test]
fn can_find_siblings() {
let mut dense = DenseSlotMap::new();
let page1 = create_page_with_weight(1);
let key1 = dense.insert(page1.clone());
let page2 = create_page_with_weight(2);
let key2 = dense.insert(page2.clone());
let page3 = create_page_with_weight(3);
let key3 = dense.insert(page3.clone());
2019-07-19 09:10:28 +00:00
let input = vec![key1, key2, key3];
2018-10-02 14:42:34 +00:00
2019-07-19 09:10:28 +00:00
let pages = find_siblings(&input);
2018-10-02 14:42:34 +00:00
assert_eq!(pages[0].1, None);
assert_eq!(pages[0].2, Some(key2));
assert_eq!(pages[1].1, Some(key1));
assert_eq!(pages[1].2, Some(key3));
assert_eq!(pages[2].1, Some(key2));
assert_eq!(pages[2].2, None);
}
}